Outline: start for loop, iterating through files (https://www.geeksforgeeks.org/how-to-iterate-over-files-in-directory-using-python/) use opencv to grab bottom right corner of image (https://stackoverflow.com/a/58984370) convert the output to greyscale then binary use pytesseract image-to-string on output to find page number (saving this to a variable inside the loop) rename the input file to the page number variable end loop